摘要
根据模糊神经网络在非线性函数逼近方面的特性和小波变换具有良好的时频两维信号的分析能力,建立了结合两者优点的单隐含层模糊递归小波神经网络(Single hidden Layer Fuzzy Recurrent Wavelet Neural Network,SLFRWNN),并分析了SLFRWNN的结构、激活函数形式及激活函数对网络性能的影响.在此基础上,提出了一种基于SLFRWNN的自适应观测器设计方法,并通过引入Lyapunov函数,证明了这种观测器设计方法的稳定性,进而给出该网络观测器的初始化和最佳训练算法;仿真结果表明SLFRWNN观测器能很好地观测系统的状态.
The fuzzy neural network has good nonlinear function approximation properties, and wavelet transform has good time-frequency signal analysis capabilities. The single hidden layer fuzzy recurrent wavelet neural network (SLFRWNN) is developed by combining with the advantages of both in this paper. The structure of networks, the form of its activation functions and its influence on SLFRWNN are analyzed. Then a design method of adaptive observer based on the single hidden layer recurrent fuzzy wavelet neural network is proposed. The Lyapunov function is introduced to prove the stability of this observer design method. And the network observer of initialization and the optimal learning algorithm is given. The final simulation results show that the single hidden layer neural fuzzy recurrent wavelet network observer can easily observe the state of the system. Copyright © 2015 by Editorial Department of Chinese Journal of Radio Science
出处
《电波科学学报》
EI
CSCD
北大核心
2015年第6期1197-1204,共8页
Chinese Journal of Radio Science
基金
国家自然科学基金(基金号:61571309
61101161)
关键词
模糊神经网络
自适应观测器
非线性系统
仿真
Design
Fuzzy inference
Fuzzy neural networks
Lyapunov functions
Mathematical transformations
Nonlinear systems
Wavelet transforms
